Papers › HandReader: Advanced Techniques for Efficient Fingerspelling Recognition

HandReader: Advanced Techniques for Efficient Fingerspelling Recognition

15 May 2025arXiv:2505.10267archive 2025-07-28

Pavel Korotaev, Petr Surovtsev, Alexander Kapitanov, Karina Kvanchiani, Aleksandr Nagaev

Fingerspelling is a significant component of Sign Language (SL), allowing the interpretation of proper names, characterized by fast hand movements during signing. Although previous works on fingerspelling recognition have focused on processing the temporal dimension of videos, there remains room for improving the accuracy of these approaches. This paper introduces HandReader, a group of three architectures designed to address the fingerspelling recognition task. HandReader_(RGB) employs the novel Temporal Shift-Adaptive Module (TSAM) to process RGB features from videos of varying lengths while preserving important sequential information. HandReader_(KP) is built on the proposed Temporal Pose Encoder (TPE) operated on keypoints as tensors. Such keypoints composition in a batch allows the encoder to pass them through 2D and 3D convolution layers, utilizing temporal and spatial information and accumulating keypoints coordinates. We also introduce HandReader_RGB+KP - architecture with a joint encoder to benefit from RGB and keypoint modalities. Each HandReader model possesses distinct advantages and achieves state-of-the-art results on the ChicagoFSWild and ChicagoFSWild+ datasets. Moreover, the models demonstrate high performance on the first open dataset for Russian fingerspelling, Znaki, presented in this paper. The Znaki dataset and HandReader pre-trained models are publicly available.

PaperPDFCode

Code

ai-forever/handreader officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Sign Language Recognition

Datasets

Introduced by this paper, per the archive.

Znaki

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Sign Language Recognition ChicagoFSWild HandReader_RGB_KP CER (%) 27.1 #1 of 3 Archive leaderboard report
Sign Language Recognition ChicagoFSWild HandReader_KP CER (%) 28 #2 of 3 Archive leaderboard report
Sign Language Recognition ChicagoFSWild HandReader_RGB CER (%) 30.7 #3 of 3 Archive leaderboard report
Sign Language Recognition ChicagoFSWild+ HandReader_RGB+KP CER (%) 24.4 #1 of 3 Archive leaderboard report
Sign Language Recognition ChicagoFSWild+ HandReader_KP CER (%) 26.2 #2 of 3 Archive leaderboard report
Sign Language Recognition ChicagoFSWild+ HandReader_RGB CER (%) 27.6 #3 of 3 Archive leaderboard report
Sign Language Recognition Znaki HandReader_RGB_KP CER (%) 5.06 #1 of 3 Archive leaderboard report
Sign Language Recognition Znaki HandReader_KP CER (%) 7.35 #2 of 3 Archive leaderboard report
Sign Language Recognition Znaki HandReader_RGB CER (%) 7.61 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

3D ConvolutionConvolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections